© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154926
    Prev
    Next
    INDEX
    Explanations

    resources in tablet Kazakhstan Set giving new Neil multiplayer injury

    np_acts-logits-general · gemini-2.5-flash-lite

    API, flags, array, options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ेटा
    0.50
    XD
    0.49
     no
    0.46
    ?.
    0.46
     Piazza
    0.46
    習
    0.46
     blank
    0.44
     Mallory
    0.43
     Lewis
    0.43
    Lewis
    0.43
    POSITIVE LOGITS
    lagt
    0.57
    тьми
    0.50
    uigen
    0.49
    ু
    0.48
    self
    0.47
    olim
    0.47
    మి
    0.46
    arabangsa
    0.46
    stuk
    0.46
    itekten
    0.45
    Activations Density 0.000%

    No Known Activations